{"id":"https://openalex.org/W4415537304","doi":"https://doi.org/10.1145/3746027.3754845","title":"Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs","display_name":"Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537304","doi":"https://doi.org/10.1145/3746027.3754845"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101333470","display_name":"Tiancheng Gu","orcid":"https://orcid.org/0009-0001-2302-246X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tiancheng Gu","raw_affiliation_strings":["The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0001-2302-246X","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaicheng Yang","orcid":"https://orcid.org/0009-0008-6073-9014"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaicheng Yang","raw_affiliation_strings":["DeepGlint, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6073-9014","affiliations":[{"raw_affiliation_string":"DeepGlint, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100531299","display_name":"Ziyong Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyong Feng","raw_affiliation_strings":["DeepGlint, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-8689-8366","affiliations":[{"raw_affiliation_string":"DeepGlint, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingjun Wang","orcid":"https://orcid.org/0009-0008-8543-1390"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjun Wang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-8543-1390","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanzhao Zhang","orcid":"https://orcid.org/0009-0003-6581-7783"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhao Zhang","raw_affiliation_strings":["Alibaba Group, Hanghzou, China"],"raw_orcid":"https://orcid.org/0009-0003-6581-7783","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hanghzou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049484480","display_name":"Dingkun Long","orcid":"https://orcid.org/0000-0001-6570-9406"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingkun Long","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6570-9406","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042773283","display_name":"Yingda Chen","orcid":"https://orcid.org/0009-0000-7358-819X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingda Chen","raw_affiliation_strings":["Alibaba Group, Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0009-0000-7358-819X","affiliations":[{"raw_affiliation_string":"Alibaba Group, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076697411","display_name":"Weidong Cai","orcid":"https://orcid.org/0000-0003-3706-8896"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weidong Cai","raw_affiliation_strings":["The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3706-8896","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073110676","display_name":"Jiankang Deng","orcid":"https://orcid.org/0000-0002-3709-6216"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiankang Deng","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3709-6216","affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2860","last_page":"2869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.635699987411499},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4537999927997589},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3416000008583069},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.27619999647140503},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.2621999979019165},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.25999999046325684}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.635699987411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5304999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4862000048160553},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32409998774528503},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28380000591278076},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W3081168214","https://openalex.org/W4385570393","https://openalex.org/W4390873312","https://openalex.org/W4404575065","https://openalex.org/W4409363896","https://openalex.org/W4413144993","https://openalex.org/W4413145832","https://openalex.org/W4413145898"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
